High-Speed Ocr Decode Using Depleted Centerlines

1. A method comprising: identifying a candidate character for optical character recognition; selecting a template from a plurality of templates to cast over the candidate character, wherein the template comprises a plurality of centerline points; determining, using a processor, an assigned score for the selected template based on the plurality of centerline points by at least: conducting a template matching analysis for the plurality of centerline points by at least counting a number of points that overlap with the candidate character and calculating a distance from each of the number of points that overlap with the candidate character to a boundary of the candidate character; and calculating the assigned score based at least in part on the template matching analysis; identifying a preferred template having a highest assigned score from the plurality of templates by comparing the assigned score of the selected template to a score for at least another template of the plurality of templates; and using the preferred template to interpret the candidate character.

2. The method of claim 1 , wherein determining, using the processor, the assigned score for the selected template further comprises: determining positions of the plurality of centerline points with respect to a principal tracing path of the candidate character; and calculating the assigned score based on the determined positions of the plurality of centerline points.

3. The method according to claim 2 , wherein calculating the assigned score further comprises calculating a proximity of the plurality of centerline points to a center of the principal tracing path.

4. The method according to claim 2 , wherein calculating the assigned score further comprises calculating a distance of the plurality of centerline points to one or more boundaries of the candidate character.

5. The method according to claim 1 , wherein conducting the template matching analysis further comprises: determining points that overlap with the candidate character; and calculating a distance from each of the determined points that overlap with the candidate character to a boundary of the candidate character.

6. The method according to claim 1 , wherein conducting the template matching analysis further comprises counting a number of points overlapping with the candidate character.

7. The method of claim 1 , wherein the template comprises an OCRB font character.

8. A apparatus comprising: a processor and a non-transitory memory including program code, the non-transitory memory and the program code configured to, with the processor, cause the apparatus to at least: identify a candidate character for optical character recognition; select a template from a plurality of templates to cast over the candidate character, wherein the template comprises a template set of centerline points; determine an assigned score for the selected template based on the template set of centerline points, wherein to determine the assigned score for the selected template based on the plurality of centerline points the apparatus is caused to: conduct a template matching analysis for the plurality of centerline points by at least counting a number of points that overlap with the candidate character and calculating a distance from each of the number of points that overlap with the candidate character to a boundary of the candidate character; and calculate the assigned score based at least in part on the template matching analysis; identify a preferred template from the plurality of templates having a highest assigned score by comparing the assigned score of the selected template to a score for at least another template of the plurality of templates; and use the preferred template to identify the candidate character.

9. The apparatus of claim 8 , wherein the at least one non-transitory memory and the program code that is configured to, with the processor, cause the apparatus to at least determine the assigned score for the selected template is further configured to: determine positions of the template set of centerline points with respect to a principal tracing path of the candidate character; and calculate the assigned score based on the determined positions of the template set of centerline points.

10. The apparatus according to claim 9 , wherein the at least one non-transitory memory and the program code that is configured to, with the processor, cause the apparatus to at least calculate the assigned score is further configured to calculate a proximity of the template set of centerline points to a center of the principal tracing path.

11. The apparatus according to claim 9 , wherein the at least one non-transitory memory and the program code that is configured to, with the processor, cause the apparatus to at least calculate the assigned score is further configured to calculate a distance of the template set of centerline points to one or more boundaries of the candidate character.

12. The apparatus according to claim 8 , wherein the at least one non-transitory memory and the program code that is configured to, with the processor, cause the apparatus to at least conduct the template matching analysis is further configured to: determine points that overlap with the candidate character; and calculate a distance from each of determined points that overlap with the candidate character to a boundary of the candidate character.

13. The apparatus according to claim 8 , wherein the at least one non-transitory memory and the program code that is configured to, with the processor, cause the apparatus to at least conduct the template matching analysis is further configured to count a number of points overlapping with the candidate character.

14. The apparatus of claim 8 , wherein the template comprises an OCRB font character.

15. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising an executable portion configured to: identify a candidate character for optical character recognition; select a centerline template from a plurality of centerline templates to cast over the candidate character, wherein the centerline template comprises centerline points; determine an assigned score for the selected centerline template, wherein to determine the assigned score the executable portion is configured to: conduct a template matching analysis for the plurality of centerline points by at least counting a number of points that overlap with the candidate character and calculating a distance from each of the number of points that overlap with the candidate character to a boundary of the candidate character; and calculate the assigned score based at least in part on the template matching analysis; identify a preferred centerline template from the plurality of centerline templates having a highest assigned score by comparing the assigned score of the centerline template to a score for at least another centerline template of the plurality of centerline templates; and use the preferred centerline template to identify the candidate character.

16. The computer program product of claim 15 , wherein the computer-readable program code portions comprising the executable portion are configured to further: determine positions of the centerline points with respect to a principal tracing path of the candidate character; and calculate the assigned score based on the determined positions of the centerline points.

17. The computer program product according to claim 16 , wherein the computer-readable program code portions comprising the executable portion are configured to further to at least one of calculate a proximity of the centerline points to a center of the principal tracing path and calculate a distance of the centerline points to one or more boundaries of the candidate character.

18. The computer program product of claim 15 , wherein the template comprises an OCRB font character.